Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:906d89c73a29ae5fbdab0bccaab839653cd2b21a62aa9bce4b0f92aabee18bb9
+oid sha256:96ae921e895bcd8204a64656686dafacd5b789b4cc44388ec452082c1b0961a1
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca5e1bed11b97f60ffab38e8ddf3d42527147fa7577c8cd93c566d10be62de2
+oid sha256:f4e897ab2d964ac8f8076065575d25846b306ddccd8c181c45365480a8ce10bf
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68562acc50572f6cb365f5d14b11accf166d4aa6a44cf504f5e5b802c9d1c19f
+oid sha256:599b9972ee45f3a6b4a0614ff019c3d8d9975b9f24af949c6d4998026461b28b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5575221238938053,
+  "epoch": 0.6371681415929203,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 7.78,
       "eval_steps_per_second": 1.966,
       "step": 63
+    },
+    {
+      "epoch": 0.584070796460177,
+      "grad_norm": 3.3250638807658106e-05,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.6106194690265486,
+      "grad_norm": 0.0001759525912348181,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.6371681415929203,
+      "grad_norm": 0.00013978495553601533,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.6371681415929203,
+      "eval_loss": 2.387317579177761e-07,
+      "eval_runtime": 12.2393,
+      "eval_samples_per_second": 7.762,
+      "eval_steps_per_second": 1.961,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.112767072043008e+16,
+  "total_flos": 1.0400790686466048e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null